Lightning: Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system

Rini T. Kaushik, Ludmila Cherkasova, Roy Campbell, Klara Nahrstedt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning uses data-classification driven data placement to realize guaranteed, substantially long, periods (several days) of idleness in a significant subset of servers designated as the Cold Zone, in the commodity datacenter backing the Cloud Storage. These servers are then transitioned to inactive power modes and the resulting energy savings substantially reduce the operating costs of the datacenter. Furthermore, the energy savings allow Lightning to improve the data access performance by incorporation of high-performance, though high-cost Solid State Drives (SSD) without exceeding the total cost of ownership (TCO) of the datacenter. Analytical cost model analysis of Lightning suggests savings in the upwards of $24 million in the TCO of a 20,000 server datacenter. The simulation results show that Lightning can achieve 46% energy costs reduction even when the datacenter is at 80% capacity utilization.

Original languageEnglish (US)
Title of host publicationHPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing
Pages332-335
Number of pages4
DOIs
StatePublished - Dec 16 2010
Event19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010 - Chicago, IL, United States
Duration: Jun 21 2010Jun 25 2010

Publication series

NameHPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing

Other

Other19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010
CountryUnited States
CityChicago, IL
Period6/21/106/25/10

Fingerprint

Lightning
Servers
Costs
Energy conservation
Cost reduction
Operating costs

Keywords

  • Cloud storage
  • Energy management
  • Performance

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Cite this

Kaushik, R. T., Cherkasova, L., Campbell, R., & Nahrstedt, K. (2010). Lightning: Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system. In HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing (pp. 332-335). (HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing). https://doi.org/10.1145/1851476.1851523

Lightning : Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system. / Kaushik, Rini T.; Cherkasova, Ludmila; Campbell, Roy; Nahrstedt, Klara.

HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. 2010. p. 332-335 (HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kaushik, RT, Cherkasova, L, Campbell, R & Nahrstedt, K 2010, Lightning: Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system. in HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, pp. 332-335, 19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010, Chicago, IL, United States, 6/21/10. https://doi.org/10.1145/1851476.1851523
Kaushik RT, Cherkasova L, Campbell R, Nahrstedt K. Lightning: Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system. In HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. 2010. p. 332-335. (HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing). https://doi.org/10.1145/1851476.1851523
Kaushik, Rini T. ; Cherkasova, Ludmila ; Campbell, Roy ; Nahrstedt, Klara. / Lightning : Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system. HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. 2010. pp. 332-335 (HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing).
@inproceedings{ee87ebadc465420b8302ac837502831e,
title = "Lightning: Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system",
abstract = "The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning uses data-classification driven data placement to realize guaranteed, substantially long, periods (several days) of idleness in a significant subset of servers designated as the Cold Zone, in the commodity datacenter backing the Cloud Storage. These servers are then transitioned to inactive power modes and the resulting energy savings substantially reduce the operating costs of the datacenter. Furthermore, the energy savings allow Lightning to improve the data access performance by incorporation of high-performance, though high-cost Solid State Drives (SSD) without exceeding the total cost of ownership (TCO) of the datacenter. Analytical cost model analysis of Lightning suggests savings in the upwards of $24 million in the TCO of a 20,000 server datacenter. The simulation results show that Lightning can achieve 46{\%} energy costs reduction even when the datacenter is at 80{\%} capacity utilization.",
keywords = "Cloud storage, Energy management, Performance",
author = "Kaushik, {Rini T.} and Ludmila Cherkasova and Roy Campbell and Klara Nahrstedt",
year = "2010",
month = "12",
day = "16",
doi = "10.1145/1851476.1851523",
language = "English (US)",
isbn = "9781605589428",
series = "HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing",
pages = "332--335",
booktitle = "HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing",

}

TY - GEN

T1 - Lightning

T2 - Self-adaptive, energy-conserving, multi-zoned, Commodity Green Cloud Storage system

AU - Kaushik, Rini T.

AU - Cherkasova, Ludmila

AU - Campbell, Roy

AU - Nahrstedt, Klara

PY - 2010/12/16

Y1 - 2010/12/16

N2 - The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning uses data-classification driven data placement to realize guaranteed, substantially long, periods (several days) of idleness in a significant subset of servers designated as the Cold Zone, in the commodity datacenter backing the Cloud Storage. These servers are then transitioned to inactive power modes and the resulting energy savings substantially reduce the operating costs of the datacenter. Furthermore, the energy savings allow Lightning to improve the data access performance by incorporation of high-performance, though high-cost Solid State Drives (SSD) without exceeding the total cost of ownership (TCO) of the datacenter. Analytical cost model analysis of Lightning suggests savings in the upwards of $24 million in the TCO of a 20,000 server datacenter. The simulation results show that Lightning can achieve 46% energy costs reduction even when the datacenter is at 80% capacity utilization.

AB - The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning uses data-classification driven data placement to realize guaranteed, substantially long, periods (several days) of idleness in a significant subset of servers designated as the Cold Zone, in the commodity datacenter backing the Cloud Storage. These servers are then transitioned to inactive power modes and the resulting energy savings substantially reduce the operating costs of the datacenter. Furthermore, the energy savings allow Lightning to improve the data access performance by incorporation of high-performance, though high-cost Solid State Drives (SSD) without exceeding the total cost of ownership (TCO) of the datacenter. Analytical cost model analysis of Lightning suggests savings in the upwards of $24 million in the TCO of a 20,000 server datacenter. The simulation results show that Lightning can achieve 46% energy costs reduction even when the datacenter is at 80% capacity utilization.

KW - Cloud storage

KW - Energy management

KW - Performance

UR - http://www.scopus.com/inward/record.url?scp=78650033305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650033305&partnerID=8YFLogxK

U2 - 10.1145/1851476.1851523

DO - 10.1145/1851476.1851523

M3 - Conference contribution

AN - SCOPUS:78650033305

SN - 9781605589428

T3 - HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing

SP - 332

EP - 335

BT - HPDC 2010 - Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing

ER -